Електронний архів

Національного університету "Львівська політехніка"

Архів зберігає опубліковані наукові матеріали переважно працівників Університету. Також доступна можливість "самоархівування"


Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 4 of 4

Recent Submissions

India’s stock market value prediction using deep neural networks
(Національний університет «Львівська політехніка», 2022) Singh, Deep Shankar Pratap; Національний університет «Львівська політехніка»
Master's qualification work was performed by a student of the group KNSSH-21f Deep Shankar Pratap Singh. Theme " India’s Stock Market Value Prediction Using Deep Neural Networks ". The work is aimed at obtaining a master's degree in the specialty 122 "Computer Science". The research was done from February, 2022 till December, 2022. The purpose of the thesis is to build a deep neural network for predicting stock prices of the NIFTY50 index for the Indian stock market and to develop a strategy system to use the built network in investments by investors and researchers. As a result, two neural networks were developed, namely LSTM and GRU. This network architecture was chosen because both are good at capturing the patterns of time-series data, which in our case is stock market data. A total of twenty-four models were created and then compared for their performance. LSTM has been observed to have higher performance than GRU and both models are very good at predicting stock market data.
Alzheimer’s disease diagnosis using machine learning approach
(Національний університет «Львівська політехніка», 2022) Bajpai, Akshay; Національний університет «Львівська політехніка»
The master's qualification work was completed by Akshay Bajpai, a student of the KNSSh-21 group. Topic " Alzheimer’s Disease Diagnosis Using Machine Learning Approach". The work is aimed at obtaining a master's degree in the specialty 122 "Computer Science". The aim of the thesis is to build multiple neural networks to diagnose Alzheimer’s disease in older adults at an early stage for using the constructed models in practice. The aim of this research is to assist medical professionals in the early diagnosis of Alzheimer’s disease before it has fully metastasised and medical practices become useless. In this research I have used a total of nine machine learning models which include standalone models as well as ensemble machine learning models to automate the process of diagnosis of this illness and compare the efficiency of each model. Each model uses the best parameters to make predictions which revealed that the employed classification model using random forest performed the best among all the other models. The best parameters for each model were automatically set by employing for loops and conditional statements.
Fish recognition system with elements of machine learning
(Національний університет «Львівська політехніка», 2023) Sabih, Khalid; Національний університет «Львівська політехніка»
This paper is wrotten by Khalid Sabih, student of group KH-417f in the field of computer science in Lviv Polytechnic National University. The subject area of the paper is fish recognition system with machine learning elements. This paper examines the need of machine learning systems in the fishing industrie, and for what they are needed. Fishing as an industrie is one of the biggest one out there with loads of fishermen that needs loads of information. The object of research is to provide useful and important information for fishermen. The subject of the research is image recognition systems and data classification. Research method is a transfer learning algorithms. This work is focusing more towards the fishermen that are amateurs and doing it just for fun, and telling them they can make profit of it, adding to that it can be as a side job for them. As an amateur it is hard to know all kind of fish species and how much money the costs. That is the reason behind this paper to offer them this kind of information with easy steps. Using transfer learning through VGG16 and with the right data, it was able to creat a model with 94.18%. For a prototype was Streamlit a great tool for that. With all of this it was possible to creat Catchfish which is an image recognition system that allows amateur fishermen with a scan and a click to have all the information needed about the fish catched.
Stacking machine learning model for predicting magnetic properties of rare-earth metals
(Національний університет «Львівська політехніка», 2023) Hasib, Ossama Ahmed Ossama; Національний університет «Львівська політехніка»
The bachelor's qualification work was completed by a student of the KN-417f group Hasib Ossama Ahmed Ossama. The topic is "Stacking machine learning model for predicting magnetic properties of rare-earth metals". The work is aimed at obtaining a bachelor's degree in 122 "Computer Science". The object of research is the processes of prediction the magnetic properties for alloys from rare earth metals. The subject of research is stacking machine learning approach for the prediction of magnetic remanence of Sm-Co magnets. The research is attained by increasing the prediction accuracy for the magnetic properties of alloys from rare earth metals using machine learning based ensemble model, furthermore several machine learning algorithms were employed to assess the performance of the alloys magnetic properties based on a real dataset specifically designed for magnetic property analysis. As a result of the research, A stacking machine learning models was created using the orange data mining software, The results obtained were compared and investigated its effectiveness, This system can be used in the future work to predict the magnetic properties of the alloys before its manufactured, So it can reduce the expenses and labor requirements associated with manufacturing.
Development of integrated information system coffee industry
(Національний університет «Львівська політехніка», 2023) Savas, Aybars; Національний університет «Львівська політехніка»
The bachelor’s qualification work was completed by a student of the KN-417F group Aybars Savas. The aim of the study is to enable customers to buy coffee safely and either buy or rent a coffee machine through the website. Coffee is a $20 billion industry. After crude oil, it is the highest earning industry in the world. It has a strong reputation for also being one of the progressive industries in the world, pumping millions of dollars a year into establishing fair trade schemes and sustainability innovations. And yet, with such a high worth, problems remain. Corruption within the industry extends across the supply chain, and environmental damage continues to occur. It’s a massive industry machine that stretches across the entire world economy, and yet change is at your fingertips. Since the demand in the coffee industry is high, online marketing makes life easier so that people can buy and rent both coffee beans and coffee machines safely and quickly. While coding the website, clean code work and responsive design were applied. Users can easily use and perform their transactions both on mobile and on the website. The website is completely designed in accordance with the principles of object-oriented programming and the codes are written in this way. The website consists of 3 different sections: Header: The header section covers the area where the website logo and burger menu are. Main: The main section is where the main content that is intended to be shown to the user or customer is located. Footer: The footer section is the section that provides information about the company, shares social media platforms, shows the address and contains license information.